jason/mempalace
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
438 Commits 2 Branches 0 Tags
9e8281aab50ed55dc313816ef8bd8abf01095963
Commit Graph

15 Commits

Author SHA1 Message Date
sha2fiddy a15094ce60 feat: include created_at timestamp in search results (#846) 
* feat: include created_at timestamp in search results (closes #465)

Surface the existing filed_at metadata as created_at in search result
objects returned by search_memories(). Enables temporal reasoning over
search hits without additional queries.

* Feat: add fallback for missing filed_at metadata
 2026-04-15 00:26:57 -07:00
Arnold Wender 6a73eb2e20 fix(searcher): guard against empty ChromaDB query results (#195) (#865) 
Fixes #195.

When ChromaDB returns no documents (empty palace, or wing/room filter
that excludes everything), it returns the shape:

    {"documents": [], "metadatas": [], "distances": []}

Indexing `results["documents"][0]` blindly raises IndexError instead of
the expected 'no results' response. Affected: searcher.search(),
searcher.search_memories() (drawer + closet branches plus the
total_before_filter aggregate), and Layer3.search() / Layer3.search_raw().

Adds a tiny private helper `searcher._first_or_empty(results, key)` that
safely extracts the inner list, returning [] for any of: missing key,
empty outer list, [None], or [[]]. layers.py imports the same helper to
avoid duplicating the guard.

Tests: tests/test_empty_chromadb_results.py covers all observed shapes
plus a documentation-style test that pins the original IndexError so
future readers understand why the helper exists.
 2026-04-15 00:26:38 -07:00
Igor Lins e Silva 6b7dcc53d4 merge: pr/closet-llm-generic + harden LLM regen path for production 
Brings in PR #793 (optional LLM-based closet regeneration via
user-configured OpenAI-compatible endpoint) and PR #795 (hybrid
closet+drawer search — closets boost, never gate). Stack: #784 → #788
→ #789 → #790 → #791 → #792 → #793 (+ #795).

Findings hardened on our side
─────────────────────────────

1) closet_llm.regenerate_closets didn't use the blessed palace helpers.

   Before:
     * manual closets_col.get(where=...) + .delete(ids=...) with a
       silent ``except Exception: pass`` around both — if the purge
       failed, pre-existing regex closets survived alongside fresh LLM
       closets, giving the searcher double hits for the same source.
     * ``source.split('/')[-1][:30]`` to build the closet_id — quietly
       wrong on Windows paths (``C:\\proj\\a.md`` has no ``/``, so the
       whole string ends up in the ID).
     * no mine_lock around purge+upsert — a concurrent regex rebuild of
       the same source could interleave with our purge and leave a mix
       of regex and LLM pointers.
     * no ``normalize_version`` stamp on the LLM closets — the miner's
       stale-version gate would treat them as leftovers from an older
       schema and rebuild over them on the next mine.

   After: routes through ``purge_file_closets`` + ``mine_lock`` +
   ``os.path.basename`` + ``NORMALIZE_VERSION`` stamp. Regression tests
   cover each.

2) searcher.search_memories was still closet-first.

   PR #795 merged into #793's head to fix the recall regression
   documented in that PR (R@1 0.25 on narrative content vs. 0.42
   baseline). The hybrid design makes closets a ranking boost rather
   than a gate: drawers are always queried at the floor, and matching
   closet hits (rank 0-4 within CLOSET_DISTANCE_CAP=1.5) add a boost
   of 0.40/0.25/0.15/0.08/0.04 to the effective distance.

   Merged to take the incoming hybrid design, with two cleanups:
   * kept the ``_expand_with_neighbors`` / ``_extract_drawer_ids_from_closet``
     helpers as separately-tested utilities (still imported by tests
     and future callers);
   * replaced the fragile ``source_file.endswith(basename)`` reverse-
     lookup in the enrichment step with internal ``_source_file_full``
     / ``_chunk_index`` fields stripped before return, so enrichment
     doesn't silently pick the wrong path when two sources share a
     basename across directories;
   * drawer-grep enrichment now sorts by ``chunk_index`` before
     neighbor expansion, so ``best_idx ± 1`` corresponds to actual
     document order rather than whatever order Chroma returned.

3) Closet-first tests in test_closets.py (``TestSearchMemoriesClosetFirst``,
   end-to-end ``test_closet_first_search_includes_drawer_index_and_total``)
   pinned contracts that the hybrid path now violates (``matched_via``
   went from ``"closet"`` to ``"drawer+closet"``). Rewrote them around
   the new invariant: direct drawers are always the floor, closet
   agreement flips the hit's matched_via and exposes closet_preview.

Verification
────────────

* 805/805 pass under ``uv run pytest tests/ -v --ignore=tests/benchmarks``
  (13 new tests from PR #793 + 5 from PR #795 + 2 new regressions for
  the closet_llm hardening + the rewritten hybrid assertions in
  test_closets.py).
* CI-pinned ruff 0.4.x clean on ``mempalace/`` + ``tests/`` (check +
  format both pass).
* No new deps — closet_llm.py still uses stdlib ``urllib.request`` per
  the PR's "zero new dependencies" promise.

Co-Authored-By: MSL <232237854+milla-jovovich@users.noreply.github.com>
 2026-04-13 18:40:36 -03:00
Igor Lins e Silva e9201fb617 merge: pr/cross-wing-tunnels + rebuild drawer-grep on hardened closet path 
Merges the full hardened stack (#788 closets, #789 entity/BM25/diary,
#790 tunnels) and reimplements the drawer-grep feature in a way that
composes with the chunk-level closet-first search instead of fighting it.

## Background

The original PR added "drawer-grep" on top of the pre-hardening closet
code that returned whole-file blobs. My #788 hardening changed that
path to return *chunk-level* hits by parsing each closet's
``→drawer_id`` pointers and hydrating exactly those drawers. That made
the original drawer-grep grep-over-all-drawers logic redundant — the
closet already points at the relevant chunk.

What remained valuable from the original PR was the *context expansion*
idea: a chunk boundary can clip a thought mid-stride (matched chunk
says "here's a breakdown:" and the breakdown lives in the next chunk),
so callers want ±1 neighbor chunks for free rather than a follow-up
get_drawer call.

## Change

New ``_expand_with_neighbors(drawers_col, doc, meta, radius=1)`` helper
in searcher.py:

* Reads ``source_file`` + ``chunk_index`` from the matched drawer's
  metadata.
* Fetches the ±radius sibling chunks in a SINGLE ChromaDB query using
  ``$and + $in`` — no "fetch all drawers for source" blowup.
* Sorts retrieved chunks by chunk_index, joins with ``\n\n``.
* Does a cheap metadata-only second query to compute ``total_drawers``
  so callers know where in the file they landed.
* Graceful fallback to the matched doc alone on any ChromaDB failure or
  missing metadata — search never breaks because expansion failed.

``_closet_first_hits`` now calls this helper and tags each hit with
``drawer_index`` + ``total_drawers``. Hit shape stays consistent with
the direct-search path (both still carry ``matched_via``) so callers
can't tell which path produced a given hit except via that field.

## Tests

6 new cases in TestDrawerGrepExpansion:
* neighbors returned in chunk_index order (not hash order)
* edge case: matched chunk at index 0 — only next neighbor surfaces
* edge case: matched chunk at last index — only prev neighbor surfaces
* edge case: 1-drawer file — returns just the matched doc
* missing/non-int chunk_index metadata — graceful fallback
* end-to-end via ``search_memories`` — closet-first hit carries
  drawer_index, total_drawers, and includes ±1 neighbors

761/761 suite pass; ruff + format clean on CI-pinned 0.4.x.

Merge resolutions: miner.py kept develop's purge+NORMALIZE_VERSION;
searcher.py dropped the old whole-file-blob block entirely in favor of
rebuilding context expansion on top of ``_closet_first_hits``;
test_closets.py took develop's 47-test baseline and appended
TestDrawerGrepExpansion.
 2026-04-13 18:08:01 -03:00
Igor Lins e Silva 32d7f4376b merge: develop + harden entity metadata, BM25, and diary ingest for production 
Merges develop (closet hardening #826, strip_noise #785, lock #784) and
replaces every sub-feature in this PR with a correct, tested
implementation. Shippable now.

## 1. Real Okapi-BM25 (searcher.py)

The prior `_bm25_score()` hardcoded `idf = log(2.0)` for every term — it
was really a scaled TF, not BM25, and couldn't tell a discriminative
term from a generic one. Replaced with `_bm25_scores(query, documents)`
that computes proper IDF over the provided candidate corpus using the
Lucene smoothed formula `log((N - df + 0.5) / (df + 0.5) + 1)`. Well-
defined for re-ranking vector-retrieval candidates — IDF there measures
how discriminative each term is *within the candidate set*, exactly the
signal we want.

`_hybrid_rank` also fixed:
- Vector normalization is now absolute `max(0, 1 - dist)`, not
  `1 - dist/max_dist` — adding/removing a candidate no longer reshuffles
  the others.
- BM25 is min-max normalized within candidates (bounded [0, 1]).
- Closet path now re-ranks too (was previously returning closet-order
  hits without hybrid scoring).
- `_hybrid_score` internal field stripped from output; `bm25_score`
  exposed for debugging.

## 2. Entity metadata (miner.py)

- Reuses `_ENTITY_STOPLIST` from palace.py so sentence-starters like
  "When", "After", "The" no longer land as entities (regression test
  covers this).
- Known-entity registry is cached at module level, keyed by the
  registry file's mtime — no more disk read per drawer.
- File handle now uses a context manager.
- Truncates the entity LIST (to 25) before joining — never splits a
  name in the middle.

## 3. Diary ingest (diary_ingest.py)

- State file now lives at `~/.mempalace/state/diary_ingest_<hash>.json`,
  keyed by (palace_path, diary_dir). No more pollution of the user's
  content directory.
- Drawer IDs now hash `(wing, date_str)` — a user with personal + work
  diaries on the same day no longer silently clobbers.
- Each day's upsert runs inside `mine_lock(source_file)` so concurrent
  ingest from two terminals can't race.
- `force=True` now calls `purge_file_closets` before rebuild so
  leftover numbered closets from a longer prior day don't orphan.

## 4. Tests (tests/test_closets.py)

Merged this PR's MineLock/Entity/BM25/Diary tests with develop's
hardened Build/Upsert/Purge/Rebuild/SearchClosetFirst tests. Added
specific regression tests for every fix above:
- entity stoplist applies (no "When/After/The")
- entity list capped before join (no partial tokens)
- registry cached by mtime (mock-verified zero re-reads)
- BM25 IDF downweights terms present in every doc (real BM25 evidence)
- hybrid rank absolute normalization stable against outliers
- diary state file outside user's diary dir
- diary wing-prefixed IDs prevent cross-wing date collisions

35/35 closet tests pass; full suite 743/743. ruff + format clean under
CI-pinned 0.4.x.
 2026-04-13 17:37:45 -03:00
Igor Lins e Silva 21d4a23430 merge: develop + harden closet layer for production 
Merges develop (#820 version sync, #785 strip_noise + NORMALIZE_VERSION,
#784 file locking) and addresses six concerns surfaced during PR review
of the closet feature:

1. Closet append-on-rebuild bug — upsert_closet_lines used to APPEND to
   existing closets (mismatched the doc's "fully replaced" promise). With
   NORMALIZE_VERSION rebuilds on develop, this would have stacked stale
   v1 topics on top of fresh v2 content forever. Fix:
   - Drop the read-and-append branch from upsert_closet_lines (now a pure
     numbered-id overwrite).
   - Add purge_file_closets(closets_col, source_file) helper that wipes
     every closet for a source file by where-filter.
   - process_file calls purge_file_closets before upsert on every mine,
     mirroring the existing drawer purge.

2. Searcher returned whole-file blobs from the closet path while the
   direct path returned chunk-level drawers. Refactored:
   - _extract_drawer_ids_from_closet parses the `→drawer_a,drawer_b`
     pointers out of closet documents.
   - _closet_first_hits hydrates exactly those drawer IDs (chunk-level),
     not collection.get(where=source_file) (which returned everything).
   - Same hit shape as direct-search path; both now carry matched_via.

3. max_distance was bypassed on the closet path. Now applied per-hit;
   when every closet candidate gets filtered, _closet_first_hits returns
   None and the caller falls through to direct drawer search.

4. Entity extraction caught sentence-starters like "When", "The",
   "After" as proper nouns. Added _ENTITY_STOPLIST (~40 common false
   positives + day/month names + role words). Real names like Igor /
   Milla still survive — covered by tests.

5. CLOSETS.md drifted from the code (claimed "replaced via upsert" but
   code appended; claimed BM25 hybrid that doesn't exist; claimed a
   10K char hydration cap that wasn't enforced). Rewritten to describe
   what actually ships, with explicit notes on the BM25 / convo-closet
   follow-ups.

6. Zero tests for ~250 lines. Added tests/test_closets.py with 17 cases:
   - build_closet_lines: pointer shape, header extraction, stoplist
     filtering (with regression case for "When/After/The"), real-name
     survival, fallback-line guarantee, drawer-ref slicing.
   - upsert_closet_lines: pure overwrite semantics (regression for the
     append bug), char-limit packing without splitting lines.
   - purge_file_closets: scoped to source_file, doesn't touch others.
   - End-to-end miner rebuild: re-mining a file with fewer topics fully
     purges leftover numbered closets from the larger first run.
   - _extract_drawer_ids_from_closet: parsing + dedup edge cases.
   - search_memories closet-first: fallback when empty, chunk-level
     hits with matched_via, no whole-file glue, max_distance enforced.

Merge resolutions: miner.py imports combined NORMALIZE_VERSION/mine_lock
from develop with the closet helpers from this branch. process_file
auto-merged cleanly (closet block sits inside develop's lock body).

724/724 tests pass. ruff + format clean under CI-pinned 0.4.x.
 2026-04-13 17:00:55 -03:00
Igor Lins e Silva 8e446f904c fix(search): hybrid closet+drawer retrieval — closets boost, never gate (#795) 2026-04-13 04:43:54 -07:00
MSL 971b92da5d feat(search): drawer-grep returns best-matching chunk + neighbors 
When a closet hit leads to a source file with many drawers, grep each
chunk for query terms and return the BEST-MATCHING chunk + 1 neighbor
on each side, instead of dumping the whole file truncated at
MAX_HYDRATION_CHARS. Result now includes drawer_index and
total_drawers so callers can request adjacent drawers explicitly.

Extracted from Milla's commit 935f657 which bundled drawer-grep with
closet_llm (deferred pending LLM_ENDPOINT refactor) and fact_checker
(separate PR). Ported only the searcher.py change.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-13 07:46:07 -03:00
MSL f935e85ead feat: entity metadata + diary ingest + BM25 hybrid search 
Three features that close the gap between the architecture docs
and the actual codebase:

1. Entity metadata on drawers and closets
   - _extract_entities_for_metadata() pulls names from known_entities.json
     + proper nouns appearing 2+ times
   - Stamped as "entities" field in ChromaDB metadata
   - Enables filterable search by person/project name

2. Day-based diary ingest (diary_ingest.py)
   - ONE drawer per day, upserted as the day grows
   - Closets pack topics atomically, never split mid-topic
   - Tracks entry count in state file, only processes new entries
   - Usage: python -m mempalace.diary_ingest --dir ~/summaries

3. BM25 hybrid search in searcher.py
   - _bm25_score() keyword matching complements vector similarity
   - _hybrid_rank() combines both signals (60% vector, 40% BM25)
   - Catches exact name/term matches that embeddings miss
   - Applied to both closet-first and direct drawer search paths

689/689 tests pass.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-13 07:40:32 -03:00
MSL d3d7184f4e feat: add closet layer — searchable index pointing to drawers 
The closet architecture was always part of MemPalace's design but
never shipped in the public codebase. This adds it.

Palace now has TWO collections:
- mempalace_drawers — full verbatim content (unchanged)
- mempalace_closets — compact AAAK-style index entries

How it works:
- When mining, each file gets a closet alongside its drawers
- Closet contains extracted topics, entities, quotes as pointers
- Closets pack up to 1500 chars, topics never split mid-entry
- Search hits closets first (fast, small), then hydrates the
  full drawer content for matching files
- Falls back to direct drawer search if no closets exist yet

Files changed:
- palace.py: get_closets_collection(), build_closet_text(),
  upsert_closet(), CLOSET_CHAR_LIMIT
- miner.py: process_file() now creates closets after drawers
- searcher.py: search_memories() tries closet-first search,
  hydrates drawers, falls back to direct search

Backwards compatible — existing palaces without closets continue
to work via the fallback path. Closets are created on next mine.

689/689 tests pass.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-13 07:37:17 -03:00
Ben Sigman 20c8f8e57b feat: new MCP tools — get/list/update drawer, hook settings, export (resolves #635) (#667) 
* feat: MCP reliability — inode detection, WAL rotation, metadata cache, search limits

Infrastructure hardening for the MCP server:
- Detect palace DB replacement via inode tracking (repair command support)
- WAL rotation to prevent unbounded WAL growth
- _fetch_all_metadata() + _get_cached_metadata() with 60s TTL for taxonomy/status
- _MAX_RESULTS cap (100) with limit clamping [1, _MAX_RESULTS]
- max_distance parameter for similarity threshold in search
- Handle all notifications/* methods, null arguments, method=None
- Remove duplicate _client_cache = None declarations
- searcher.py max_distance parameter passthrough

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* feat: new MCP tools (get/list/update drawer, hook settings, memories filed), export, normalize

New MCP tools:
- mempalace_get_drawer: fetch single drawer by ID with full content
- mempalace_list_drawers: paginated listing with wing/room filter
- mempalace_update_drawer: update content/wing/room on existing drawers
- mempalace_hook_settings: get/set hook behavior (silent_save, desktop_toast)
- mempalace_memories_filed_away: check latest checkpoint status

Also includes:
- exporter.py: export palace as browsable markdown files
- normalize.py: tool_use/tool_result capture for richer transcript mining
- layers.py: updated for new tool integration
- config.py: hook settings properties (hook_silent_save, hook_desktop_toast)

Depends on PR 3 (reliability) for _MAX_RESULTS, _metadata_cache, WAL logging.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: normalize.py handles string messages and Read offset type mismatch

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: params null guard, L2→cosine docs, empty tool_use_map key guard

- Handle explicit null in MCP params (request.get("params") or {})
- Fix search tool description: L2 → cosine distance (collection uses hnsw:space=cosine)
- Guard against empty string key in tool_use_map from malformed JSONL entries

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: rename ambiguous var 'l' to 'line' (E741 lint)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: address code review findings (5 issues)

1. min_similarity backwards-compat: convert similarity to distance scale
   (1.0 - similarity) instead of passing raw value as max_distance
2. Restore structured error reporting (error + partial fields) in
   tool_status, tool_list_wings, tool_list_rooms, tool_get_taxonomy
   — reverts silent except:pass that dropped #647 security hardening
3. inode cache: remove falsy-zero short-circuit so missing DB file
   triggers reconnect instead of reusing stale client
4. _fetch_all_metadata: check for empty batch before extending/advancing
   offset to prevent infinite loop on concurrent deletion
5. KG initialization: only override path when --palace is explicit;
   default runs use KnowledgeGraph's built-in default path

Co-authored-by: jphein <jphein@users.noreply.github.com>

---------

Co-authored-by: jp <jp@jphein.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: jphein <jphein@users.noreply.github.com>
 2026-04-11 21:25:04 -07:00
Sergey Kuznetsov ae5196bc8d Мempalace backend seam (#413) 
* refactor: add stage-1 backend abstraction seam

Introduce the first upstreamable storage seam for MemPalace without
bringing in the PostgreSQL spike or any benchmark artifacts.

This change adds a small backend package with:
- BaseCollection as the minimal collection contract
- ChromaBackend/ChromaCollection as the default implementation

It then routes the main runtime collection consumers through that seam:
- palace.py
- searcher.py
- layers.py
- palace_graph.py
- mcp_server.py
- miner.status()

Behavioral constraints kept for stage 1:
- ChromaDB remains the only backend and the default path
- no config/env backend selection yet
- no PostgreSQL code
- no benchmark or research files
- existing tests stay unchanged

Important compatibility details:
- read paths now call the seam with create=False so they still surface
  the existing 'no palace found' behavior instead of silently creating
  empty collections
- write paths keep create=True semantics through palace.get_collection()
- layers/searcher retain a chromadb module attribute so the existing
  mock-based tests can keep patching PersistentClient unchanged
- ChromaBackend only creates palace directories on create=True, which
  preserves mocked read-path tests that use fake read-only paths

Verification:
- python3 -m py_compile mempalace/backends/__init__.py mempalace/backends/base.py mempalace/backends/chroma.py mempalace/palace.py mempalace/searcher.py mempalace/layers.py mempalace/palace_graph.py mempalace/mcp_server.py mempalace/miner.py
- pytest -q  # 529 passed, 106 deselected

* refactor: clean up stage-1 seam compatibility shims

Tighten the stage-1 backend abstraction branch after review.

This follow-up does three small things:
- keep the chromadb compatibility hook in searcher.py and layers.py,
  but express it through the backends.chroma module so it no longer
  reads like an accidental unused import
- fix the palace_graph.py helper alias to avoid the local name collision
  flagged by ruff (imported helper vs local _get_collection wrapper)
- preserve the existing mock-based test patch points unchanged while
  keeping the new backend seam intact

Why this matters:
- the direct  form looked like a
  dead import in review, even though it was intentionally preserving the
  existing test seam ( and
  )
- palace_graph.py had a real lint issue ( redefinition) that was
  small but worth fixing before a public PR

Verification:
- /opt/homebrew/bin/ruff check mempalace/backends/__init__.py mempalace/backends/base.py mempalace/backends/chroma.py mempalace/palace.py mempalace/searcher.py mempalace/layers.py mempalace/palace_graph.py mempalace/mcp_server.py mempalace/miner.py
- pytest -q tests/test_layers.py tests/test_searcher.py
- pytest -q  # 529 passed, 106 deselected

* docs: explain backend shim imports in search paths

Add short code comments in searcher.py and layers.py explaining why the
module-level `chromadb` alias remains after the stage-1 backend seam
refactor.

The alias is intentional: it preserves the existing mock patch points used
by the current test suite (`mempalace.searcher.chromadb.PersistentClient`
and `mempalace.layers.chromadb.PersistentClient`) while the runtime logic
now flows through the backend abstraction.

This keeps the public PR easier to review because the apparent "unused
import" now has an explicit reason next to it.

Verification:
- /opt/homebrew/bin/ruff check mempalace/searcher.py mempalace/layers.py
- pytest -q tests/test_layers.py tests/test_searcher.py

* refactor: reuse a default backend instance in palace helper

Tighten the stage-1 backend seam by promoting the default Chroma backend
adapter to a module-level singleton in `mempalace/palace.py`.

This keeps the stage-1 scope unchanged — Chroma is still the only backend
wired in this branch — but avoids constructing a fresh `ChromaBackend()`
object on every `get_collection()` call. The backend is stateless today,
so this is a readability/cleanup change rather than a behavioral one.

Why this helps:
- makes `palace.get_collection()` read like a real default factory instead
  of an inline constructor call
- keeps the stage-1 branch a little cleaner before opening the public PR
- does not widen the backend surface or change any config/runtime behavior

Verification:
- python3 -m py_compile mempalace/palace.py
- pytest -q tests/test_miner.py tests/test_layers.py tests/test_searcher.py
- pytest -q  # 529 passed, 106 deselected

* fix: harden read-only seam behavior and update seam tests

Preserve the stage-1 backend abstraction while closing the real read-path
regression surfaced in PR review.

What changed:
- make ChromaBackend.get_collection(create=False) fail fast when the palace
  directory does not exist instead of letting PersistentClient create it as a
  side effect
- update miner.status() to call get_collection(..., create=False) so status
  keeps the historical 'No palace found' behavior
- remove the temporary chromadb shim aliases from layers.py and searcher.py
  now that the tests patch the seam directly
- add focused tests for the new backends package, including ChromaCollection
  delegation and ChromaBackend create=True/create=False behavior
- retarget layer/searcher tests to patch the backend seam instead of patching
  chromadb.PersistentClient inside production modules
- add a regression test that status() does not create an empty palace when the
  target path is missing

Verification:
- ruff check .
- uv run pytest -q
- uv run pytest -q tests/test_backends.py tests/test_cli.py tests/test_mcp_server.py tests/test_layers.py tests/test_searcher.py tests/test_miner.py

Notes:
- the separate benchmark/slow/stress layer was started as a soak but not used
  as the merge gate for this PR branch

* refactor: drop duplicate mcp collection cache declaration

Remove a redundant `_collection_cache = None` assignment in
`mempalace/mcp_server.py` left over after the stage-1 backend seam refactor.

This does not change behavior; it only trims review noise in the MCP server
module after the read-path hardening pass.

Verification:
- ruff check mempalace/mcp_server.py
- uv run pytest -q tests/test_mcp_server.py

---------

Co-authored-by: Sergey Kuznetsov <sergey@iterudit.com>
 2026-04-11 16:16:49 -07:00
Igor Lins e Silva 5ac4947d02 fix: preserve CLI exit codes, log tracebacks, sanitize search errors, validate fixture 2026-04-07 18:26:39 -03:00
Igor Lins e Silva c9135aad67 fix: sanitize error responses and remove sys.exit from library code 
- Remove palace_path from _no_palace() error response (prevents
  leaking filesystem paths to the LLM)
- Replace str(e) with generic 'Internal tool error' in MCP dispatch
  catch block (full error is still logged server-side via stderr)
- Replace sys.exit(1) with return in searcher.search() CLI function
  (prevents process termination if called from library context)
- Remove unused sys import from searcher.py

Findings: #12 (HIGH), #5 (MEDIUM), #15 (LOW)

Includes test infrastructure from PR #131.
92 tests pass.
 2026-04-07 18:24:10 -03:00
Milla Jovovich 068dbd9a7b MemPalace: palace architecture, AAAK compression, knowledge graph 
The memory system:
- Palace structure: Wings (people/projects) → Rooms (topics) → Closets (AAAK compressed) → Drawers (verbatim transcripts)
- Halls connect related rooms within a wing
- Tunnels cross-reference rooms across wings
- AAAK: 30x lossless compression dialect for AI agents
- Knowledge graph: temporal entity-relationship triples (SQLite)
- Palace graph: room-based navigation with tunnel detection
- MCP server: 19 tools — search, graph traversal, agent diary, AAAK auto-teach
- Onboarding: guided setup generates wing config + AAAK entity registry
- Contradiction detection: catches wrong pronouns, names, ages
- Auto-save hooks for Claude Code

96.6% Recall@5 on LongMemEval — highest zero-API score published.
100% with optional Haiku rerank (500/500).
Local. Free. No API key required.
 2026-04-04 18:16:04 -07:00